Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 05 7月, 2019 3 次提交
  3. 24 6月, 2019 2 次提交
  5. 19 6月, 2019 2 次提交
  7. 12 6月, 2019 1 次提交
  9. 11 6月, 2019 3 次提交
  11. 28 5月, 2019 1 次提交
    • K
      RDMA/core: Fix panic when port_data isn't initialized · 46bdf370
      由 Kamal Heib 提交于 
      This happens if assign_name() returns failure when called from
ib_register_device(), that will lead to the following panic in every time
that someone touches the port_data's data members.

 BUG: unable to handle kernel NULL pointer dereference at 00000000000000c0
 PGD 0 P4D 0
 Oops: 0002 [#1] SMP PTI
 CPU: 19 PID: 1994 Comm: systemd-udevd Not tainted 5.1.0-rc5+ #1
 Hardware name: HP ProLiant DL360p Gen8, BIOS P71 12/20/2013
 RIP: 0010:_raw_spin_lock_irqsave+0x1e/0x40
 Code: 85 ff 66 2e 0f 1f 84 00 00 00 00 00 66 66 66 66 90 53 9c 58 66 66 90
 66 90 48 89 c3 fa 66 66 90 66 66 90 31 c0 ba 01 00 00 00 <f0> 0f b1 17 0f
 94 c2 84 d2 74 05 48 89 d8 5b c3 89 c6 e8 b4 85 8a
 RSP: 0018:ffffa8d7079a7c08 EFLAGS: 00010046
 RAX: 0000000000000000 RBX: 0000000000000202 RCX: ffffa8d7079a7bf8
 RDX: 0000000000000001 RSI: ffff93607c990000 RDI: 00000000000000c0
 RBP: 0000000000000001 R08: 0000000000000000 R09: ffffffffc08c4dd8
 R10: 0000000000000000 R11: 0000000000000001 R12: 00000000000000c0
 R13: ffff93607c990000 R14: ffffffffc05a9740 R15: ffffa8d7079a7e98
 FS:  00007f1c6ee438c0(0000) GS:ffff93609f6c0000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00000000000000c0 CR3: 0000000819fca002 CR4: 00000000000606e0
 Call Trace:
  free_netdevs+0x4d/0xe0 [ib_core]
  ib_dealloc_device+0x51/0xb0 [ib_core]
  __mlx5_ib_add+0x5e/0x70 [mlx5_ib]
  mlx5_add_device+0x57/0xe0 [mlx5_core]
  mlx5_register_interface+0x85/0xc0 [mlx5_core]
  ? 0xffffffffc0474000
  do_one_initcall+0x4e/0x1d4
  ? _cond_resched+0x15/0x30
  ? kmem_cache_alloc_trace+0x15f/0x1c0
  do_init_module+0x5a/0x218
  load_module+0x186b/0x1e40
  ? m_show+0x1c0/0x1c0
  __do_sys_finit_module+0x94/0xe0
  do_syscall_64+0x5b/0x180
  entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 8ceb1357 ("RDMA/device: Consolidate ib_device per_port data into one place")
Signed-off-by: NKamal Heib <kamalheib1@gmail.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      46bdf370
  13. 22 5月, 2019 2 次提交
    • K
      RDMA/core: Return void from ib_device_check_mandatory() · deee3c7e
      由 Kamal Heib 提交于 
      The return value from ib_device_check_mandatory() is always 0 - change it
to be void.
Signed-off-by: NKamal Heib <kamalheib1@gmail.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      deee3c7e
    • L
      RDMA/srp: Rename SRP sysfs name after IB device rename trigger · dc1435c0
      由 Leon Romanovsky 提交于 
      SRP logic used device name and port index as symlink to relevant
kobject. If the IB device is renamed then the prior name will be re-used
by the next device plugged in and sysfs will panic as SRP will try to
re-use the same name.

 mlx5_ib: Mellanox Connect-IB Infiniband driver v5.0-0
 sysfs: cannot create duplicate filename '/class/infiniband_srp/srp-mlx5_0-1'
 CPU: 3 PID: 1107 Comm: modprobe Not tainted 5.1.0-for-upstream-perf-2019-05-12_15-09-52-87 #1
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
 Call Trace:
  dump_stack+0x5a/0x73
  sysfs_warn_dup+0x58/0x70
  sysfs_do_create_link_sd.isra.2+0xa3/0xb0
  device_add+0x33f/0x660
  srp_add_one+0x301/0x4f0 [ib_srp]
  add_client_context+0x99/0xe0 [ib_core]
  enable_device_and_get+0xd1/0x1b0 [ib_core]
  ib_register_device+0x533/0x710 [ib_core]
  ? mutex_lock+0xe/0x30
  __mlx5_ib_add+0x23/0x70 [mlx5_ib]
  mlx5_add_device+0x4e/0xd0 [mlx5_core]
  mlx5_register_interface+0x85/0xc0 [mlx5_core]
  ? 0xffffffffa0791000
  do_one_initcall+0x4b/0x1cb
  ? kmem_cache_alloc_trace+0xc6/0x1d0
  ? do_init_module+0x22/0x21f
  do_init_module+0x5a/0x21f
  load_module+0x17f2/0x1ca0
  ? m_show+0x1c0/0x1c0
  __do_sys_finit_module+0x94/0xe0
  do_syscall_64+0x48/0x120
  entry_SYSCALL_64_after_hwframe+0x44/0xa9
 RIP: 0033:0x7f157cce10d9

The module load/unload sequence was used to trigger such kernel panic:
 sudo modprobe ib_srp
 sudo modprobe -r mlx5_ib
 sudo modprobe -r mlx5_core
 sudo modprobe mlx5_core

Have SRP track the name of the core device so that it can't have a name
collision.

Fixes: d21943dd ("RDMA/core: Implement IB device rename function")
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NBart Van Assche <bvanassche@acm.org>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      dc1435c0
  15. 08 5月, 2019 1 次提交
  17. 03 5月, 2019 2 次提交
  19. 02 5月, 2019 1 次提交
  21. 23 4月, 2019 3 次提交
    • P
      RDMA/core: Add a netlink command to change net namespace of rdma device · 2e5b8a01
      由 Parav Pandit 提交于 
      Provide an option to change the net namespace of a rdma device through a
netlink command. When multiple rdma devices exists in a system, and when
containers are used, this will limit rdma device visibility to a specified
net namespace.

An example command to change net namespace of mlx5_1 device to the
previously created net namespace 'foo' is:

$ ip netns add foo
$ rdma dev set mlx5_1 netns foo
Signed-off-by: NParav Pandit <parav@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      2e5b8a01
    • P
      RDMA/core: Introduce a helper function to change net namespace of rdma device · decbc7a6
      由 Parav Pandit 提交于 
      Introduce a helper function that changes rdma device's net namespace which
performs mini disable/enable sequence to have device visible only in
assigned net namespace.

Device unregistration, device rename and device change net namespace
may be invoked concurrently.

(a) device unregistration needs to wait if a device change (rename or net
    namespace change) operation is in progress.
(b) device net namespace change should not proceed if the unregistration
    has started.
(c) while one cpu is changing device net namespace, other cpu should not
    be able to rename or change net namespace.

To address above concurrency,
(a) Use unreg_mutex to synchronize between ib_unregister_device() and net
    namespace change operation
(b) In cases where unregister_device() has started unregistration before
    change_netns got chance to acquire unreg_mutex, validate the refcount
    - if it dropped to zero, abort the net namespace change operation.

Finally use the helper function to change net namespace of ib device to
move the device back to init_net when such net is deleted.
Signed-off-by: NParav Pandit <parav@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      decbc7a6
    • P
      RDMA/core: Avoid freeing netdevs in disable_device() · 3042492b
      由 Parav Pandit 提交于 
      So we can use the disable_device() helper while changing the net namespace
of the rdma device in a subsequent patch, move free_netdevs() out of it.
Signed-off-by: NParav Pandit <parav@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      3042492b
  23. 09 4月, 2019 3 次提交
  25. 29 3月, 2019 9 次提交
  27. 23 2月, 2019 1 次提交
  29. 20 2月, 2019 6 次提交
    • J
      RDMA/rxe: Close a race after ib_register_device · ca22354b
      由 Jason Gunthorpe 提交于 
      Since rxe allows unregistration from other threads the rxe pointer can
become invalid any moment after ib_register_driver returns. This could
cause a user triggered use after free.

Add another driver callback to be called right after the device becomes
registered to complete any device setup required post-registration.  This
callback has enough core locking to prevent the device from becoming
unregistered.
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      ca22354b
    • J
      RDMA/rxe: Add ib_device_get_by_name() and use it in rxe · 6cc2c8e5
      由 Jason Gunthorpe 提交于 
      rxe has an open coded version of this that is not as safe as the core
version. This lets us eliminate the internal device list entirely from
rxe.
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      6cc2c8e5
    • J
      RDMA/device: Provide APIs from the core code to help unregistration · d0899892
      由 Jason Gunthorpe 提交于 
      These APIs are intended to support drivers that exist outside the usual
driver core probe()/remove() callbacks. Normally the driver core will
prevent remove() from running concurrently with probe(), once this safety
is lost drivers need more support to get the locking and lifetimes right.

ib_unregister_driver() is intended to be used during module_exit of a
driver using these APIs. It unregisters all the associated ib_devices.

ib_unregister_device_and_put() is to be used by a driver-specific removal
function (ie removal by name, removal from a netdev notifier, removal from
netlink)

ib_unregister_queued() is to be used from netdev notifier chains where
RTNL is held.

The locking is tricky here since once things become async it is possible
to race unregister with registration. This is largely solved by relying on
the registration refcount, unregistration will only ever work on something
that has a positive registration refcount - and then an unregistration
mutex serializes all competing unregistrations of the same device.
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      d0899892
    • J
      RDMA/device: Add ib_device_get_by_netdev() · 324e227e
      由 Jason Gunthorpe 提交于 
      Several drivers need to find the ib_device from a given netdev. rxe needs
this at speed in an unsleepable context, so choose to implement the
translation using a RCU safe hash table.

The hash table can have a many to one mapping. This is intended to support
some future case where multiple IB drivers (ie iWarp and RoCE) connect to
the same netdevs. driver_ids will need to be different to support this.

In the process this makes the struct ib_device and ib_port_data RCU safe
by deferring their kfrees.
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      324e227e
    • J
      RDMA/device: Add ib_device_set_netdev() as an alternative to get_netdev · c2261dd7
      由 Jason Gunthorpe 提交于 
      The associated netdev should not actually be very dynamic, so for most
drivers there is no reason for a callback like this. Provide an API to
inform the core code about the net dev affiliation and use a core
maintained data structure instead.

This allows the core code to be more aware of the ndev relationship which
will allow some new APIs based around this.

This also uses locking that makes some kind of sense, many drivers had a
confusing RCU lock, or missing locking which isn't right.
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      c2261dd7
    • J
      RDMA/device: Consolidate ib_device per_port data into one place · 8ceb1357
      由 Jason Gunthorpe 提交于 
      There is no reason to have three allocations of per-port data. Combine
them together and make the lifetime for all the per-port data match the
struct ib_device.

Following patches will require more port-specific data, now there is a
good place to put it.
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>
      8ceb1357